© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14881
    Prev
    Next
    INDEX
    Explanations

    fluctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RootManager
    0.53
     ngại
    0.51
    ڇ
    0.50
    有料
    0.49
    陋
    0.49
     bersih
    0.47
     ausreichend
    0.47
    जाम
    0.47
    👪
    0.47
    LOR
    0.46
    POSITIVE LOGITS
     fluctuating
    3.56
     fluctuation
    3.39
     fluctuations
    3.34
     fluctuate
    3.19
     fluctuates
    3.16
     fluctu
    3.08
     oscillating
    2.92
     fluct
    2.91
     alternating
    2.81
     oscillate
    2.72
    Activations Density 0.178%

    No Known Activations